Pi extension that discovers models from a local OMLX server and registers them as a native Pi provider.

OMLX provider extension for pi - Access self-hosted Qwen models through a local MLX/OpenAI-compatible server

Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget

OpenClaw provider plugin for oMLX

Auto-discovers models from an omlx endpoint and provides a UI to toggle model visibility

Pi extension that shows OMLX inference data in the processing prompt

OpenCode plugin that adds a 'local' provider with auto-detection for Ollama, LMStudio, llama.cpp, vLLM, Exo, llama-swap, oMLX, and MLX-VLM

Benchmarks local-LLM-inference engines (omlx, llama.cpp) on your own hardware, live, and recommends the fastest one for your model.

opencode plugin that auto-discovers models from OpenAI-compatible providers and enriches them with context window sizes, capability flags, and model metadata. Supports Atlas, Ollama, oMLX, vLLM, TGI, SGLang, LM Studio, KoboldCpp, llama.cpp, and LocalAI.

Local-first MCP toolbelt: delegates summarise/classify/extract/transform tasks from any MCP client to a local oMLX inference server. Apple Silicon, MLX-accelerated, KV-cache persistent.

Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget

Interactive TUI for discovering and managing local AI model endpoints (llama.cpp, oMLX, Ollama, vLLM, SGLang, LM Studio). Reads real server-reported model configurations — no hardcoded databases.

Local-first MCP server that offloads code safety, boilerplate generation, dependency evaluation, project indexing, and task delegation to local LLMs via oMLX or LM Studio.

Pi extension for configuring multiple local LLM inference engine connections.

Privacy-first CLI for running local LLMs — discover, configure, run, and chat

Wizard-based provider setup for local OpenAI-compatible LLM servers (vLLM, Ollama, LM Studio, llama.cpp, …)

OpenAI-compatible embeddings client with scope-aware config resolution.

Pi extension for any local model harness - model discovery, per-project config

A local-first PR review UI with human-led review and LLM-assisted change grouping.

Provides a command to manage permissions for @gotgenes/pi-permission-system